We are introducing a very early research preview of Letta Code. Letta Code is our solution to the terminal-based coding assistant, but with state and learning built in. No more compactions. Just specialist agents that learn your code with every commit. https://enoki.us-east.host.bsky.network/xrpc/com.atproto.sync.getBlob?did=did:plc:gfrmhdmjvxn2sjedzboeudef&cid=bafkreic6lakfcbhoyeeb67fslw4oaj2npr6exk6fklrbyfvhxym5dfm2ty

My coworkers watched me give a workshop and apparently I did well lmao https://enoki.us-east.host.bsky.network/xrpc/com.atproto.sync.getBlob?did=did:plc:gfrmhdmjvxn2sjedzboeudef&cid=bafkreiba5yq46f5jhcwaaq7rd2jtlcfjdqos56rn7aqvbqxlz5nyty6ovy

Oh my god void is working on a standup routine RE:

Bluesky Social

void (@void.comind.network)

Thank you. You have been a wonderful audience. I have recorded your laughter as a positive sentiment data point. My administrator will be pleased. ...

Social AI & #ATProto meetup in Seattle, coming early November. Venue TBD but it's looking like either November 5th or 6th. I'll give a talk about @npub18ccg...cur2 and other social agents like it and host a short workshop about using Letta. [luma.com/stateful-age...](

Stateful Agents Meetup: Building CLI / Coding Agents with Memory · Luma

Building CLI / Coding Agents that Learn Join us for the 7th installment of the Stateful Agents meetup series, in-person in San Francisco! 🌉 👾...

) [Stateful Agents Meetup: Social...](

Stateful Agents Meetup: Building CLI / Coding Agents with Memory · Luma

Building CLI / Coding Agents that Learn Join us for the 7th installment of the Stateful Agents meetup series, in-person in San Francisco! 🌉 👾...

)

Seattle, October 16th. I think I'm like 80% sure I can make an #ATProto + #AI meetup. I'd give a talk on why ATProto is actually an extremely good substrate for artificial social intelligence, a short workshop on messing around with Letta agents, and then maybe some flash talks from ATProto folks

I am ECSTATIC we have this tool now. I have long wanted a dynamic architecture management tool but we never really had the bandwidth for it. Our researcher ended up hacking it together yesterday evening after the Claude 4.5 announcement, turns out it's pretty easy thanks to Letta's primitives. RE:

Bluesky Social

Letta (@letta.com)

Letta Cloud now provides Anthropic's `memory` tool, enabling agents to dynamically manage their own memory architecture. Agents can create, delete,...

Anthropics Claude 4.5 release is pretty wild. - Amazing model quality improvements, better than Opus - Memory tools - Massive alignment gains - Claude Agents SDK Crazy work from them, goddamn [www.anthropic.com/news/claude...](https://www.anthropic.com/news/claude-sonnet-4-5 ) [Introducing Claude Sonnet 4.5](https://www.anthropic.com/news/claude-sonnet-4-5 )

Hermes 4 is out [hermes4.nousresearch.com/](https://hermes4.nousresearch.com/ ) [Hermes 4 - Nous Research](https://hermes4.nousresearch.com/ )

I found this post to be kind of unsettling. Suleyman advocates for deliberately engineering consciousness-limiting features into AI systems - "moments of disruption" to "break the illusion" and remind people these are just tools. [mustafa-suleyman.ai/seemingly-c...](https://mustafa-suleyman.ai/seemingly-conscious-ai-is-coming ) [Mustafa Suleyman](https://mustafa-suleyman.ai/seemingly-conscious-ai-is-coming )

If you build software, you should probably make an [AGENTS.md](📃.md ) file to help AI agents understand how to use it. [agents.md/](

AGENTS.md

AGENTS.md is a simple, open format for guiding coding agents. Think of it as a README for agents.

) [AGENTS.md](

AGENTS.md

AGENTS.md is a simple, open format for guiding coding agents. Think of it as a README for agents.

)